Papers by Sai Rajeswar

4 papers
StarFlow: Generating Structured Workflow Outputs From Sketch Images (2026.eacl-long)

Copied to clipboard

Challenge: Despite being widely used, building workflows can be complex, often requiring manual configuration through low-code platforms or visual programming tools.
Approach: They propose a framework for generating structured workflow outputs from sketches using vision-language models to automate the process.
Outcome: The proposed framework outperforms large vision-language models in the task of generating structured workflow outputs from sketches and diagrams.
Grammar Search for Multi-Agent Systems (2026.acl-long)

Copied to clipboard

Challenge: Several prior approaches have relied on LLM-based free-form search over the code space.
Approach: They propose a more structured framework that explores the same space through a fixed set of composable components.
Outcome: The proposed framework outperforms existing approaches on most benchmarks across two backbone LLMs and two domains: mathematics and question answering.
ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing methods for multimodal document retrieval often replicate techniques developed for text-only retrieval.
Approach: They propose a document retrieval model that bridges the gap between multimodal representation learning and document retrievals by providing external knowledge as context.
Outcome: The proposed model achieves 3.61% improvement over existing retrieval models on the ViDoRe V2 benchmark, showing stronger generalization to out-of-domain benchmarks.
WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks focus on specific aspects of web tasks but lack comprehensive coverage.
Approach: They propose a multilingual benchmark that evaluates three core web tasks: (1) website visual question answering, (2) code editing involving HTML/CSS/JavaScript, and (3) mockup-to-code generation.
Outcome: The proposed model performs well on basic information extraction, but struggles with reasoning and grounding, editing code to preserve functionality, and generating design-to-code that maintains hierarchy and supports multilingual content.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations